{"id":"https://openalex.org/W2953761480","doi":"https://doi.org/10.21437/interspeech.2019-1804","title":"Synchronising Audio and Ultrasound by Learning Cross-Modal Embeddings","display_name":"Synchronising Audio and Ultrasound by Learning Cross-Modal Embeddings","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2953761480","doi":"https://doi.org/10.21437/interspeech.2019-1804","mag":"2953761480"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1804","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.00758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049305990","display_name":"Aciel Eshky","orcid":"https://orcid.org/0000-0002-7746-3412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aciel Eshky","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["School of Philosophy, Psychology, and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology, and Language Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4100","last_page":"4104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045320510864258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7103303074836731},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6683779954910278},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5932592749595642},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5471498370170593},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47512489557266235},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4223180413246155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3568269610404968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045320510864258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7103303074836731},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6683779954910278},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5932592749595642},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5471498370170593},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47512489557266235},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4223180413246155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3568269610404968},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2019-1804","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.00758","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.00758","pdf_url":"https://arxiv.org/pdf/1907.00758","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2953761480","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1907.00758","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pure.ed.ac.uk:openaire/46f666a8-c61a-46da-b821-23b96f68db06","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/46f666a8-c61a-46da-b821-23b96f68db06","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eshky, A, Ribeiro, M, Richmond, K & Renals, S 2019, Synchronising audio and ultrasound by learning cross-modal embeddings. in INTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA). International Speech Communication Association, Graz, Austria, pp. 4100-4104, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1804","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/46f666a8-c61a-46da-b821-23b96f68db06","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/46f666a8-c61a-46da-b821-23b96f68db06","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eshky, A, Ribeiro, M, Richmond, K & Renals, S 2019, Synchronising audio and ultrasound by learning cross-modal embeddings. in INTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA). International Speech Communication Association, Graz, Austria, pp. 4100-4104, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1804","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1907.00758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.00758","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.00758","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.00758","pdf_url":"https://arxiv.org/pdf/1907.00758","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7869365812","display_name":null,"funder_award_id":"EP/P02338X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1562651896","https://openalex.org/W1964963331","https://openalex.org/W1988910659","https://openalex.org/W1995440941","https://openalex.org/W2022423195","https://openalex.org/W2042608483","https://openalex.org/W2127211243","https://openalex.org/W2127589108","https://openalex.org/W2138621090","https://openalex.org/W2152262131","https://openalex.org/W2157364932","https://openalex.org/W2604379605","https://openalex.org/W2788354612","https://openalex.org/W2808631503","https://openalex.org/W2889418448","https://openalex.org/W2939800755","https://openalex.org/W2950864153","https://openalex.org/W2963173190","https://openalex.org/W2964048159","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2973160882","https://openalex.org/W2787748747","https://openalex.org/W2797090057","https://openalex.org/W3123318516","https://openalex.org/W3027171322","https://openalex.org/W2064194796","https://openalex.org/W1500408247","https://openalex.org/W2800753652","https://openalex.org/W2136946929","https://openalex.org/W2796069293","https://openalex.org/W2094800907","https://openalex.org/W2115420694","https://openalex.org/W2092803535","https://openalex.org/W2112931636","https://openalex.org/W3096800427","https://openalex.org/W2962696180","https://openalex.org/W2149105670","https://openalex.org/W2039562357","https://openalex.org/W144392981","https://openalex.org/W3161492781"],"abstract_inverted_index":{"Audiovisual":[0],"synchronisation":[1,48],"is":[2],"the":[3,7,18,29,41,59,75,78,83,114,128],"task":[4],"of":[5,17,28,101,116,124],"determining":[6],"time":[8],"offset":[9],"between":[10,77],"speech":[11,22,149],"audio":[12,24],"and":[13,25,53,94,108],"a":[14,69],"video":[15],"recording":[16,45],"articulators.":[19],"In":[20],"child":[21],"therapy,":[23],"ultrasound":[26],"videos":[27],"tongue":[30],"are":[31,136],"captured":[32],"using":[33],"instruments":[34],"which":[35,73],"rely":[36],"on":[37,89,127],"hardware":[38],"to":[39,57,81,118,139,143],"synchronise":[40,58,141],"two":[42,79],"modalities":[43,80],"at":[44],"time.":[46],"Hardware":[47],"can":[49],"fail":[50],"in":[51,148],"practice,":[52],"no":[54],"mechanism":[55],"exists":[56],"signals":[60],"post":[61],"hoc.":[62],"To":[63],"address":[64],"this":[65],"problem,":[66],"we":[67],"employ":[68],"two-stream":[70],"neural":[71],"network":[72],"exploits":[74],"correlation":[76],"find":[82],"offset.":[84],"We":[85],"train":[86],"our":[87],"model":[88,125],"recordings":[90],"from":[91,104],"69":[92],"speakers,":[93,110],"show":[95],"that":[96,132],"it":[97],"correctly":[98],"synchronises":[99],"82.9%":[100],"test":[102,129],"utterances":[103,117,130,144],"unseen":[105,109],"therapy":[106],"sessions":[107],"thus":[111],"considerably":[112],"reducing":[113],"number":[115],"be":[119],"manually":[120],"synchronised.":[121],"An":[122],"analysis":[123],"performance":[126],"shows":[131],"directed":[133],"phone":[134],"articulations":[135],"more":[137],"difficult":[138],"automatically":[140],"compared":[142],"containing":[145],"natural":[146],"variation":[147],"such":[150],"as":[151],"words,":[152],"sentences,":[153],"or":[154],"conversations.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}